INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĤ¨ãĥ«

-0.86

TPP

-0.81

\/\/

-0.79

ORN

-0.77

Insert

-0.75

sburg

-0.75

ãĥ¤

-0.75

capt

-0.74

INAL

-0.71

Character

-0.69

POSITIVE LOGITS

psy

0.78

 vest

0.73

oire

0.72

gym

0.65

stery

0.64

 medicine

0.64

ioned

0.63

 seas

0.62

 perfume

0.61

 clenched

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.